metadata
base_model: unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit
library_name: peft
Model Card for Model ID
This is the model that is used to get the paper results for the MPCxR1 Qwen2.5 1.5B GRPO model. This model was evaluated on the 20.04.25. and trained on the 19.04.25. Base model was Qwen/Qwen2.5-1.5B-Instruct